AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Math-72B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run Qwen/Qwen2.5-Math-72B-Instruct with Q4 quantization. At approximately 148 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 156GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 36GB | 192GB | 148.25 tok/s | ✅ Fits comfortably |
| Q8 | 71GB | 192GB | 100.63 tok/s | ✅ Fits comfortably |
| FP16 | 142GB | 192GB | 57.93 tok/s | ✅ Fits comfortably |